AI 中文总结
本研究针对圣维南系统宽范围调节问题，提出反步引导SAC控制器框架，结合DeepONet学习反步控制先验与迁移学习，在桑布尔河模型仿真中提升了学习效率与大偏差下的调节效果。
AI 中文摘要
反步控制可为非线性圣维南系统提供局部稳定性保证，但当系统运行远离标称平衡点时，其调节性能可能下降。本论文提出一种反步引导软 Actor-Critic（SAC）控制器框架，将基于模型的控制知识融入强化学习（RL）。首先通过深度算子网络（DeepONet）学习标称反步控制律，并将其作为先验信息特征表示嵌入 Actor 与 Critic 网络；再将学习到的先验与 SAC 策略结合生成最终控制输入，同时采用迁移学习策略在适应非线性动力学过程中保留有用的反步知识。对桑布尔河模型的仿真结果表明，与反步控制相比，该方法可提升学习效率，并在更大初始偏差下保持有效调节。
英文摘要
Backstepping control provides local stability guarantees for nonlinear Saint-Venant systems, but its regulation performance may degrade when the system operates far from the nominal equilibrium. This letter proposes a backstepping-guided soft actor-critic (SAC) controller framework that incorporates model-based control knowledge into reinforcement learning (RL). The nominal backstepping control law is first learned by deep operator network (DeepONet) and embedded into the actor and critic networks as prior informed feature representations. The learned prior is further combined with the SAC policy to generate the final control input, while a transfer-learning strategy preserves the useful backstepping knowledge during adaptation to the nonlinear dynamics. Simulation results on the Sambre River model demonstrate that the proposed method improves learning efficiency and maintains effective regulation over larger initial deviations than backstepping control.
